CN112733702A - Sidewalk detection method, device and equipment based on remote sensing image and storage medium - Google Patents
Sidewalk detection method, device and equipment based on remote sensing image and storage medium Download PDFInfo
- Publication number
- CN112733702A CN112733702A CN202110016501.9A CN202110016501A CN112733702A CN 112733702 A CN112733702 A CN 112733702A CN 202110016501 A CN202110016501 A CN 202110016501A CN 112733702 A CN112733702 A CN 112733702A
- Authority
- CN
- China
- Prior art keywords
- sidewalk
- road
- area
- detection
- remote sensing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a sidewalk detection method, a device, equipment and a storage medium based on remote sensing images, wherein the method comprises the steps of obtaining a training set sample, and marking a road area and a sidewalk area of the training set sample; training a road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model; carrying out road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result; training a deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model; detecting a sidewalk by using the trained deep convolution neural network model to obtain a primary sidewalk detection result; and fusing the potential road extraction result and the primary sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result. The invention considers the interdependence relationship between the sidewalk and the road and improves the detection precision of the sidewalk.
Description
Technical Field
The invention relates to the field of sidewalk detection, in particular to a sidewalk detection method, a sidewalk detection device, sidewalk detection equipment and a storage medium based on remote sensing images.
Background
The current remote sensing image sidewalk detection algorithm based on the deep learning model comprises two parts: training and detecting. In the training phase, a large number of labeled training sample sets, including positive and negative samples, need to be prepared. The positive samples are sidewalk areas or image blocks containing sidewalks, and the negative samples are image blocks of non-arbitrary non-sidewalk areas. After the training data set is prepared, the deep learning model begins to be trained. The input of the model training is an original image, and the output of the model is a detection or judgment result. Given a training image set (X, Y), X being the original image and Y being the corresponding label, the deep-learned model training can be expressed as follows:
wherein n represents the number of samples, W is a parameter of the deep learning model, and tau represents an error function. In the deep learning model, common error functions may be cross entropy, mean square error, and the like. After training, a deep learning network model parameter W is obtained, and then the process of determining whether the image block is a sidewalk image block by giving an image can be represented as follows:
L(ti)＝ti*W
the prior method can obtain satisfactory pavement detection precision through training of a large number of data sets. However, false detection is still common due to the fact that the background of the remote sensing image is too complex, the coverage range is too wide, and the number of similar targets on the ground is large. One of the main reasons is that the current methods generally directly use the trained detection model for detection, and do not consider the interdependence relationship between the sidewalk and the road.
Disclosure of Invention
The invention aims to provide a sidewalk detection method, a sidewalk detection device, sidewalk detection equipment and a sidewalk detection storage medium based on remote sensing images, so as to solve the existing problems.
Acquiring a training set sample, and marking a road area and a sidewalk area of the training set sample;
training a road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model;
carrying out road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result;
training a deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model;
detecting a sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result;
and fusing the potential road extraction result and the primary sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result.
Further, the road segmentation extraction model is a U-Net-based road segmentation extraction model.
Further, the fusion of the potential road extraction result and the initial sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result specifically comprises:
filtering the sidewalk area with the primary sidewalk detection confidence coefficient lower than a first threshold;
and filtering the detection result of the high-confidence-degree area of the primary sidewalk detection and the potential road overlapping ratio lower than a second threshold.
Further, the marking of both the road area and the sidewalk area of the training set is specifically by manual marking.
The invention also provides a sidewalk detection device based on the remote sensing image, which comprises
The marking module is used for marking the road area and the sidewalk area of the training set;
the first training module is used for acquiring a training set sample and marking a road area and a sidewalk area of the training set sample;
the extraction module is used for extracting roads by using the trained road segmentation extraction model so as to obtain a potential road extraction result;
the second training module is used for training the deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model;
the detection module is used for detecting the sidewalk by using the trained deep convolutional neural network model so as to obtain a primary sidewalk detection result;
and the fusion module is used for fusing the potential road extraction result and the initial sidewalk detection result by utilizing a mixed classification algorithm so as to obtain a final sidewalk detection result.
Further, the road segmentation extraction model is a U-Net-based road segmentation extraction model.
Further, the fusion of the potential road extraction result and the initial sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result specifically comprises:
filtering the sidewalk area with the primary sidewalk detection confidence coefficient lower than a first threshold;
and filtering the detection result of the high-confidence-degree area of the primary sidewalk detection and the potential road overlapping ratio lower than a second threshold.
Further, the marking of both the road area and the sidewalk area of the training set is specifically by manual marking.
The invention also provides sidewalk detection equipment based on the remote sensing image, which comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor is used for operating the computer program to realize the sidewalk detection method based on the remote sensing image.
The invention also provides a storage medium, wherein the storage medium stores a computer program, and the computer program can be executed by a processor of a device where the storage medium is located so as to realize the sidewalk detection method based on the remote sensing image.
The invention provides a sidewalk detection method based on remote sensing images, which comprises the steps of obtaining a training set sample, and marking a road area and a sidewalk area of the training set sample; training a road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model; carrying out road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result; training a deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model; detecting a sidewalk by using the trained deep convolution neural network model to obtain a primary sidewalk detection result; and fusing the potential road extraction result and the primary sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result. The invention can obtain a higher-precision sidewalk detection result and reduce error detection which is not in accordance with sidewalk distribution logic by considering the interdependence relationship between the sidewalks and the road, and has better detection precision, stability and robustness compared with a sidewalk detection algorithm purely based on a deep convolutional neural network.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow chart of a sidewalk detection method based on a remote sensing image according to a first embodiment of the present invention.
Fig. 2 is another schematic flow chart of a sidewalk detection method based on a remote sensing image according to a first embodiment of the present invention.
Fig. 3 is a schematic flow chart of a sidewalk detection apparatus based on a remote sensing image according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings of the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention.
Referring to fig. 1-2, a first embodiment of the present invention provides a sidewalk detection method based on remote sensing images, including:
and S11, acquiring a training set sample, and marking the road area and the sidewalk area of the training set sample.
In this embodiment, the marking of both the road area and the sidewalk area of the training set is specifically completed by manual marking, and information obtained by marking is used for model training.
And S12, training the road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model.
In the embodiment, the road segmentation extraction model is a U-Net-based road segmentation extraction model. The U-Net model firstly uses convolution to carry out down sampling, then extracts the characteristics of one layer and another layer, uses the characteristics of the layer and the another layer to carry out up sampling, and finally obtains an image of which each pixel point corresponds to the type of the pixel point. The U-Net model extracts more characteristic layers, so that the road segmentation extraction model based on the U-Net is more accurate in road extraction.
And S13, performing road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result.
And S14, training the deep convolutional neural network model by using the mark information of the sidewalk area to obtain a trained deep convolutional neural network model.
In this embodiment, the deep convolutional neural network model may select a CNN, which includes a convolutional layer and a pooling layer, where the convolutional layer is used to extract features, so that the network has a certain transition invariance and a certain dimensionality reduction function, and the pooling layer plays a role in dimensionality reduction. It should be noted that, of course, the deep convolutional neural network model may be other models, and these schemes are all within the scope of the present invention.
And S15, detecting the sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result.
And S16, fusing the potential road extraction result and the initial sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result.
In the embodiment, the potential road extraction result and the primary sidewalk detection result are fused, and a sidewalk area with the primary sidewalk detection confidence lower than a first threshold is filtered; and filtering out the detection result that the overlapping proportion of the high-confidence-degree area of the primary sidewalk detection and the potential road is lower than a second threshold value so as to obtain the final sidewalk detection result. Wherein the first threshold represents a threshold for filtering low sidewalk detection confidence, which would be filtered out if the detection confidence of a region is below the value; the second threshold value represents an overlap ratio threshold value of a pedestrian road detection high-confidence area and a potential road area, and if the threshold value is too low, the detection result is filtered.
In the embodiment, a training set sample is obtained, and a road area and a sidewalk area of the training set sample are marked; training a road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model; carrying out road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result; training a deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model; detecting a sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result; and fusing the potential road extraction result and the primary sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result. Considering the interdependency relationship between the sidewalks and the roads, the potential road extraction result and the initial sidewalk detection result are fused, so that a higher-precision sidewalk detection result can be obtained, the error detection which is not in accordance with the sidewalk distribution logic is reduced, and the detection precision, the stability and the robustness are better.
The second embodiment of the invention provides a sidewalk detection device based on remote sensing images, and with reference to fig. 3, the device comprises
And a marking module 110, configured to mark both the road area and the sidewalk area of the training set.
In this embodiment, the marking of both the road area and the sidewalk area of the training set is specifically completed by manual marking, and information obtained by marking is used for model training.
The first training module 120 is configured to obtain a training set sample, and mark both a road area and a sidewalk area of the training set sample.
In the embodiment, the road segmentation extraction model is a U-Net-based road segmentation extraction model. The U-Net model firstly uses convolution to carry out down sampling, then extracts the characteristics of one layer and another layer, uses the characteristics of the layer and the another layer to carry out up sampling, and finally obtains an image of which each pixel point corresponds to the type of the pixel point. The U-Net model extracts more characteristic layers, so that the road segmentation extraction model based on the U-Net is more accurate in road extraction.
And the extracting module 130 is configured to perform road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result.
And the second training module 140 is configured to train the deep convolutional neural network model by using the mark information of the sidewalk area, so as to obtain a trained deep convolutional neural network model.
In this embodiment, the deep convolutional neural network model may select a CNN, which includes a convolutional layer and a pooling layer, where the convolutional layer is used to extract features, so that the network has a certain transition invariance and a certain dimensionality reduction function, and the pooling layer plays a role in dimensionality reduction. It should be noted that, of course, the deep convolutional neural network model may be other models, and these schemes are all within the scope of the present invention.
And the detection module 150 is configured to perform detection on the sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result.
And the fusion module 160 is configured to fuse the potential road extraction result and the initial sidewalk detection result by using a hybrid classification algorithm to obtain a final sidewalk detection result.
In this embodiment, the fusion module 160 is configured to fuse the potential road extraction result and the first sidewalk detection result, and filter out a sidewalk area where the first sidewalk detection confidence is lower than a first threshold; and filtering out the detection result that the overlapping proportion of the high-confidence-degree area of the primary sidewalk detection and the potential road is lower than a second threshold value so as to obtain the final sidewalk detection result. Wherein the first threshold represents a threshold for filtering low sidewalk detection confidence, which would be filtered out if the detection confidence of a region is below the value; the second threshold value represents an overlap ratio threshold value of a pedestrian road detection high-confidence area and a potential road area, and if the threshold value is too low, the detection result is filtered.
In the embodiment, the marking module 110 is used for marking the road area and the sidewalk area of the training set; the first training module 120 is configured to obtain a training set sample, and mark both a road area and a sidewalk area of the training set sample; an extraction module 130, configured to perform road extraction using the trained road segmentation extraction model to obtain a potential road extraction result; the second training module 140 is configured to train a deep convolutional neural network model using the mark information of the sidewalk area to obtain a trained deep convolutional neural network model; the detection module 150 is configured to perform detection on a sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result; and the fusion module 160 is configured to fuse the potential road extraction result and the initial sidewalk detection result by using a hybrid classification algorithm to obtain a final sidewalk detection result. By considering the interdependency relationship between the sidewalks and the roads and fusing the potential road extraction result and the initial sidewalk detection result, a higher-precision sidewalk detection result can be obtained, the error detection which is not in accordance with the sidewalk distribution logic is reduced, and the detection precision, the stability and the robustness are better.
The invention provides a sidewalk detection device based on remote sensing images, which comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor is used for operating the computer program to realize the sidewalk detection method based on the remote sensing images.
A fourth embodiment of the present invention provides a storage medium, where the storage medium stores a computer program, and the computer program can be executed by a processor of a device in which the storage medium is located, so as to implement the method for detecting a sidewalk based on a remote sensing image.
In the embodiments provided in the embodiments of the present invention, it should be understood that the apparatus and method provided may be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
While the invention has been particularly shown and described with reference to a preferred embodiment, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A sidewalk detection method based on remote sensing images is characterized by comprising the following steps:
acquiring a training set sample, and marking a road area and a sidewalk area of the training set sample;
training a road segmentation extraction model by using the marking information of the road area to obtain a trained road segmentation extraction model;
carrying out road extraction by using the trained road segmentation extraction model to obtain a potential road extraction result;
training a deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model;
detecting a sidewalk by using the trained deep convolutional neural network model to obtain a primary sidewalk detection result;
and fusing the potential road extraction result and the primary sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result.
2. The method for detecting the sidewalk based on the remote sensing image according to claim 1, wherein the road segmentation extraction model is a U-Net-based road segmentation extraction model.
3. The method for detecting sidewalk based on remote sensing images according to claim 1, wherein the fusion of the potential road extraction result and the initial sidewalk detection result by using a mixed classification algorithm to obtain a final sidewalk detection result specifically comprises:
filtering the sidewalk area with the primary sidewalk detection confidence coefficient lower than a first threshold;
and filtering the detection result of the high-confidence-degree area of the primary sidewalk detection and the potential road overlapping ratio lower than a second threshold.
4. The method for sidewalk detection based on remote sensing images according to claim 1, wherein the marking of both the road area and the sidewalk area of the training set is performed by manual marking.
5. A sidewalk detection device based on remote sensing images is characterized by comprising:
the marking module is used for marking the road area and the sidewalk area of the training set;
the first training module is used for acquiring a training set sample and marking a road area and a sidewalk area of the training set sample;
the extraction module is used for extracting roads by using the trained road segmentation extraction model so as to obtain a potential road extraction result;
the second training module is used for training the deep convolutional neural network model by using the marking information of the sidewalk area to obtain a trained deep convolutional neural network model;
the detection module is used for detecting the sidewalk by using the trained deep convolutional neural network model so as to obtain a primary sidewalk detection result;
and the fusion module is used for fusing the potential road extraction result and the initial sidewalk detection result by utilizing a mixed classification algorithm so as to obtain a final sidewalk detection result.
6. The remote sensing image-based pavement detection apparatus according to claim 5, wherein the road segmentation extraction model is a U-Net-based road segmentation extraction model.
7. The remote sensing image-based pavement detection apparatus according to claim 5, wherein the fusion module is specifically configured to
Filtering the sidewalk area with the primary sidewalk detection confidence coefficient lower than a first threshold;
and filtering the detection result of the high-confidence-degree area of the primary sidewalk detection and the potential road overlapping ratio lower than a second threshold.
8. The remote sensing image-based pavement detection apparatus according to claim 5, wherein the labeling module is configured to label both the road area and the pavement area of the training set, specifically by manual labeling.
9. A remote sensing image-based pavement detection device, characterized by comprising a memory and a processor, wherein the memory stores a computer program, and the processor is used for operating the computer program to realize a remote sensing image-based pavement detection method according to any one of claims 1-4.
10. A storage medium, characterized in that the storage medium stores a computer program which can be executed by a processor of a device on which the storage medium is located, to implement a method for remote sensing image-based pavement detection according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016501.9A CN112733702A (en) | 2021-01-07 | 2021-01-07 | Sidewalk detection method, device and equipment based on remote sensing image and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110016501.9A CN112733702A (en) | 2021-01-07 | 2021-01-07 | Sidewalk detection method, device and equipment based on remote sensing image and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112733702A true CN112733702A (en) | 2021-04-30 |
Family
ID=75590875
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110016501.9A Pending CN112733702A (en) | 2021-01-07 | 2021-01-07 | Sidewalk detection method, device and equipment based on remote sensing image and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112733702A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180373943A1 (en) * | 2017-06-23 | 2018-12-27 | Panasonic Intellectual Property Corporation Of America | Computer implemented detecting method, computer implemented learning method, detecting apparatus, learning apparatus, detecting system, and recording medium |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| CN110807376A (en) * | 2019-10-17 | 2020-02-18 | 北京化工大学 | Method and device for extracting urban road based on remote sensing image |
| US20200250975A1 (en) * | 2019-01-31 | 2020-08-06 | AitronX Inc. | Sidewalk Detection for Electric Scooters |
| JP2020160291A (en) * | 2019-03-27 | 2020-10-01 | アイシン・エィ・ダブリュ株式会社 | Road information update system, route search system, and road information update program |
| CN112183258A (en) * | 2020-09-16 | 2021-01-05 | 太原理工大学 | Remote sensing image road segmentation method based on context information and attention mechanism |
-
2021
- 2021-01-07 CN CN202110016501.9A patent/CN112733702A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180373943A1 (en) * | 2017-06-23 | 2018-12-27 | Panasonic Intellectual Property Corporation Of America | Computer implemented detecting method, computer implemented learning method, detecting apparatus, learning apparatus, detecting system, and recording medium |
| US20200250975A1 (en) * | 2019-01-31 | 2020-08-06 | AitronX Inc. | Sidewalk Detection for Electric Scooters |
| CN109800736A (en) * | 2019-02-01 | 2019-05-24 | 东北大学 | A kind of method for extracting roads based on remote sensing image and deep learning |
| JP2020160291A (en) * | 2019-03-27 | 2020-10-01 | アイシン・エィ・ダブリュ株式会社 | Road information update system, route search system, and road information update program |
| CN110807376A (en) * | 2019-10-17 | 2020-02-18 | 北京化工大学 | Method and device for extracting urban road based on remote sensing image |
| CN112183258A (en) * | 2020-09-16 | 2021-01-05 | 太原理工大学 | Remote sensing image road segmentation method based on context information and attention mechanism |
Non-Patent Citations (1)
| Title |
|---|
| 胡强;屈蔷;何鑫;: "改进的多特征融合人行道检测算法", 应用科技, no. 02, pages 39 - 47 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111932553B (en) | Remote sensing image semantic segmentation method based on area description self-attention mechanism | |
| Hofmann et al. | Detecting informal settlements from QuickBird data in Rio de Janeiro using an object based approach | |
| CN109190481B (en) | Method and system for extracting road material of remote sensing image | |
| KR102190527B1 (en) | Apparatus and method for automatic synthesizing images | |
| CN110796026A (en) | Pedestrian re-identification method based on global feature stitching | |
| CN106548169B (en) | Fuzzy literal Enhancement Method and device based on deep neural network | |
| CN111160205B (en) | Method for uniformly detecting multiple embedded types of targets in traffic scene end-to-end | |
| Huang et al. | Spatial-temproal based lane detection using deep learning | |
| CN109165682A (en) | A kind of remote sensing images scene classification method merging depth characteristic and significant characteristics | |
| CN106780727B (en) | Vehicle head detection model reconstruction method and device | |
| CN112232368A (en) | Target recognition model training method, target recognition method and related device thereof | |
| CN112287983A (en) | Remote sensing image target extraction system and method based on deep learning | |
| CN111008554B (en) | Deep learning-based method for identifying pedestrians without giving away in dynamic traffic zebra stripes | |
| Bu et al. | A UAV photography–based detection method for defective road marking | |
| CN112785610B (en) | Lane line semantic segmentation method integrating low-level features | |
| CN113158954B (en) | Automatic detection method for zebra crossing region based on AI technology in traffic offsite | |
| CN108073925A (en) | A kind of licence plate recognition method and device | |
| CN114120284A (en) | Deep learning highway lane structuring method, storage medium and device | |
| CN112733702A (en) | Sidewalk detection method, device and equipment based on remote sensing image and storage medium | |
| CN116206326A (en) | Training method of missing detection model, missing detection method and device of diversion area | |
| Rafi et al. | Performance analysis of deep learning YOLO models for South Asian regional vehicle recognition | |
| CN113255524B (en) | Pavement information identification method and system based on YOLO v4 | |
| Xie et al. | [Retracted] Intelligent Recognition Technology for the Segmentation of Traffic Indication Images Concerning Different Pavement Materials | |
| CN114782678A (en) | Lane line detection method with global positioning and local detection | |
| de Mesquita et al. | Street pavement classification based on navigation through street view imagery |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |